Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.8139. Min Act: -0.0001
Data Index: 758606 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.3930. Min Act: -0.0001
Data Index: 1629661 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.5061. Min Act: -0.0001
Data Index: 596822 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.3411. Min Act: -0.0001
Data Index: 794378 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.2919. Min Act: -0.0001
Data Index: 688242 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.3956. Min Act: -0.0001
Data Index: 257778 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.2314. Min Act: -0.0001
Data Index: 122477 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.2215. Min Act: -0.0001
Data Index: 906790 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.1734. Min Act: -0.0001
Data Index: 892819 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.1511. Min Act: -0.0001
Data Index: 1635158 (Python Code)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.1222. Min Act: -0.0001
Data Index: 1324543 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0213. Min Act: -0.0001
Data Index: 223189 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8139. Min Range: -2.8139
Max Act: 1.9975. Min Act: -0.0001
Data Index: 46419 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0981. Min Act: -0.0001
Data Index: 599786 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0630. Min Act: -0.0001
Data Index: 943784 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0556. Min Act: -0.0001
Data Index: 495196 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0186. Min Act: -0.0001
Data Index: 258553 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0344. Min Act: -0.0001
Data Index: 424422 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0014. Min Act: -0.0001
Data Index: 1063165 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8139. Min Range: -2.8139
Max Act: 2.0851. Min Act: -0.0001
Data Index: 147773 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19